单目图像序列光流三维重建技术研究综述

由单目图像序列光流重建物体或场景的三维运动与结构是计算机视觉、图像处理与模式识别等领域的重要研究内容，在机器人视觉、无人机导航、车辆辅助驾驶以及医学影像分析等方面具有重要的应用。本文首先从精度与鲁棒性等方面对单目图像序列光流计算及三维重建技术近年来取得的进展进行综述与分析。然后采用Middlebury测试图像序列对HS、LDOF、CLG-TV、SOF、AOFSCNN 和 Classic ＋NL 等典型光流算法以及 Adiv、RMROF、Sekkati 和DMDPOF等基于光流的间接与直接重建方法进行实验对比分析，指出各对比方法的优点与不足，归纳各类方法的性能特点与适用范围。最后对利用分数阶微分模型、非局部约束、立体视觉以及深度线索解决亮度突变、非刚性运动、运动遮挡与模糊情况下光流计算及重建模型的局限性与鲁棒性问题进行总结与展望。

Review of the 3 D Reconstruction TechnoIogy Based on OpticaI FIow of MonocuIar I mage Sequence

The research on 3D motion estimation and structure reconstruction of the object or scene based on the mo-nocular image sequence optical flow is important in computer vision,image processing and pattern recognition,and the re-search achievements are applied in many fields.such as robot vision,unmanned aerial vehicle(UAV)navigation,driver as-sistance system,medical image analysis,and so on.Firstly,the research progress of the technologies of the monocular image sequence optical flow estimation and 3 D reconstruction is reviewed and analyzed from the aspects of accuracy and robust-ness.Secondly,the test image sequences of Middlebury database are employed to make comparison among the optical flow methods of HS,LDOF,CLG-TV,SOF,AOFSCNN and Classic+NL,and the direct and indirect reconstruction methods of Adiv,RMROF,Sekkati and DMDPOF based on optical flow are compared.Through the comparison results,the advantages and disadvantages of the methods are pointed out,and the characteristics and applications of the methods are generalized.Fi-nally,the limitations and robustness of the models of optical flow estimation and 3D reconstruction in brightness changing, non-rigid motion,motion occlusion and blur are summarized,and the solutions by the fractional order differential model, non-local constraint,stereo vision and depth cue are presented.